小爬静态页面图片

关于爬虫协议：

有的网站下是有文件：robots.txt

比如：

豆瓣

优快云

以慕课网http://www.imooc.com/首页为例

源代码：

#coding:utf-8
class Outputer:
	def __init__(self,directory):
		self.directory=directory
	def output(self,file,content):
		try:
			f=open(self.directory+file,'wb')
			f.write(content)
		except Exception as err:
			print(err)
		finally:
			f.close()
			print(file+"has writed!")


class SpiderMan:
	def __init__(self,url,directory):
		self.url=url
		self.outputer=Outputer(directory)
	def crawl(self):
		resp=request.urlopen(self.url)
		buff=resp.read()
		pattern=r'http:.+\.jpg'
		jpgurls=re.findall(pattern,buff.decode('utf-8'),flags=0)
		count=1
		for jurl in jpgurls:
			try:
				content=request.urlopen(jurl).read()
				print(count)
				count=count+1
				self.outputer.output('imooc_'+str(count)+'.jpg',content)
			except UnicodeEncodeError  as err:
				print(err)

if __name__ == '__main__':
	from  urllib import request
	import re
	#http://www.imooc.com/
	url='http://www.imooc.com/'
	spider=SpiderMan(url,'./spider_imooc/')
	spider.crawl()

运行图：

　　

转载于:https://www.cnblogs.com/jasonhaven/p/7367421.html